From 49054556289e8787501630b7c7a9d407da02e296 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 29 Sep 2021 11:59:17 +0200 Subject: net: introduce and use lock_sock_fast_nested() Syzkaller reported a false positive deadlock involving the nl socket lock and the subflow socket lock: MPTCP: kernel_bind error, err=-98 ============================================ WARNING: possible recursive locking detected 5.15.0-rc1-syzkaller #0 Not tainted -------------------------------------------- syz-executor998/6520 is trying to acquire lock: ffff8880795718a0 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x267/0x7b0 net/mptcp/protocol.c:2738 but task is already holding lock: ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1612 [inline] ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x23/0x7b0 net/mptcp/protocol.c:2720 other info that might help us debug this: Possible unsafe locking scenario: CPU0 ---- lock(k-sk_lock-AF_INET); lock(k-sk_lock-AF_INET); *** DEADLOCK *** May be due to missing lock nesting notation 3 locks held by syz-executor998/6520: #0: ffffffff8d176c50 (cb_lock){++++}-{3:3}, at: genl_rcv+0x15/0x40 net/netlink/genetlink.c:802 #1: ffffffff8d176d08 (genl_mutex){+.+.}-{3:3}, at: genl_lock net/netlink/genetlink.c:33 [inline] #1: ffffffff8d176d08 (genl_mutex){+.+.}-{3:3}, at: genl_rcv_msg+0x3e0/0x580 net/netlink/genetlink.c:790 #2: ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: lock_sock include/net/sock.h:1612 [inline] #2: ffff8880787c8c60 (k-sk_lock-AF_INET){+.+.}-{0:0}, at: mptcp_close+0x23/0x7b0 net/mptcp/protocol.c:2720 stack backtrace: CPU: 1 PID: 6520 Comm: syz-executor998 Not tainted 5.15.0-rc1-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:88 [inline] dump_stack_lvl+0xcd/0x134 lib/dump_stack.c:106 print_deadlock_bug kernel/locking/lockdep.c:2944 [inline] check_deadlock kernel/locking/lockdep.c:2987 [inline] validate_chain kernel/locking/lockdep.c:3776 [inline] __lock_acquire.cold+0x149/0x3ab kernel/locking/lockdep.c:5015 lock_acquire kernel/locking/lockdep.c:5625 [inline] lock_acquire+0x1ab/0x510 kernel/locking/lockdep.c:5590 lock_sock_fast+0x36/0x100 net/core/sock.c:3229 mptcp_close+0x267/0x7b0 net/mptcp/protocol.c:2738 inet_release+0x12e/0x280 net/ipv4/af_inet.c:431 __sock_release net/socket.c:649 [inline] sock_release+0x87/0x1b0 net/socket.c:677 mptcp_pm_nl_create_listen_socket+0x238/0x2c0 net/mptcp/pm_netlink.c:900 mptcp_nl_cmd_add_addr+0x359/0x930 net/mptcp/pm_netlink.c:1170 genl_family_rcv_msg_doit+0x228/0x320 net/netlink/genetlink.c:731 genl_family_rcv_msg net/netlink/genetlink.c:775 [inline] genl_rcv_msg+0x328/0x580 net/netlink/genetlink.c:792 netlink_rcv_skb+0x153/0x420 net/netlink/af_netlink.c:2504 genl_rcv+0x24/0x40 net/netlink/genetlink.c:803 netlink_unicast_kernel net/netlink/af_netlink.c:1314 [inline] netlink_unicast+0x533/0x7d0 net/netlink/af_netlink.c:1340 netlink_sendmsg+0x86d/0xdb0 net/netlink/af_netlink.c:1929 sock_sendmsg_nosec net/socket.c:704 [inline] sock_sendmsg+0xcf/0x120 net/socket.c:724 sock_no_sendpage+0x101/0x150 net/core/sock.c:2980 kernel_sendpage.part.0+0x1a0/0x340 net/socket.c:3504 kernel_sendpage net/socket.c:3501 [inline] sock_sendpage+0xe5/0x140 net/socket.c:1003 pipe_to_sendpage+0x2ad/0x380 fs/splice.c:364 splice_from_pipe_feed fs/splice.c:418 [inline] __splice_from_pipe+0x43e/0x8a0 fs/splice.c:562 splice_from_pipe fs/splice.c:597 [inline] generic_splice_sendpage+0xd4/0x140 fs/splice.c:746 do_splice_from fs/splice.c:767 [inline] direct_splice_actor+0x110/0x180 fs/splice.c:936 splice_direct_to_actor+0x34b/0x8c0 fs/splice.c:891 do_splice_direct+0x1b3/0x280 fs/splice.c:979 do_sendfile+0xae9/0x1240 fs/read_write.c:1249 __do_sys_sendfile64 fs/read_write.c:1314 [inline] __se_sys_sendfile64 fs/read_write.c:1300 [inline] __x64_sys_sendfile64+0x1cc/0x210 fs/read_write.c:1300 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7f215cb69969 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 e1 14 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 c0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffc96bb3868 EFLAGS: 00000246 ORIG_RAX: 0000000000000028 RAX: ffffffffffffffda RBX: 00007f215cbad072 RCX: 00007f215cb69969 RDX: 0000000000000000 RSI: 0000000000000004 RDI: 0000000000000005 RBP: 0000000000000000 R08: 00007ffc96bb3a08 R09: 00007ffc96bb3a08 R10: 0000000100000002 R11: 0000000000000246 R12: 00007ffc96bb387c R13: 431bde82d7b634db R14: 0000000000000000 R15: 0000000000000000 the problem originates from uncorrect lock annotation in the mptcp code and is only visible since commit 2dcb96bacce3 ("net: core: Correct the sock::sk_lock.owned lockdep annotations"), but is present since the port-based endpoint support initial implementation. This patch addresses the issue introducing a nested variant of lock_sock_fast() and using it in the relevant code path. Fixes: 1729cf186d8a ("mptcp: create the listening socket for new port") Fixes: 2dcb96bacce3 ("net: core: Correct the sock::sk_lock.owned lockdep annotations") Suggested-by: Thomas Gleixner Reported-and-tested-by: syzbot+1dd53f7a89b299d59eaf@syzkaller.appspotmail.com Signed-off-by: Paolo Abeni Reviewed-by: Thomas Gleixner Signed-off-by: David S. Miller --- include/net/sock.h | 31 ++++++++++++++++++++++++++++++- 1 file changed, 30 insertions(+), 1 deletion(-) (limited to 'include/net/sock.h') diff --git a/include/net/sock.h b/include/net/sock.h index c005c3c750e8..dc3f8169312e 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1623,7 +1623,36 @@ void release_sock(struct sock *sk); SINGLE_DEPTH_NESTING) #define bh_unlock_sock(__sk) spin_unlock(&((__sk)->sk_lock.slock)) -bool lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock); +bool __lock_sock_fast(struct sock *sk) __acquires(&sk->sk_lock.slock); + +/** + * lock_sock_fast - fast version of lock_sock + * @sk: socket + * + * This version should be used for very small section, where process wont block + * return false if fast path is taken: + * + * sk_lock.slock locked, owned = 0, BH disabled + * + * return true if slow path is taken: + * + * sk_lock.slock unlocked, owned = 1, BH enabled + */ +static inline bool lock_sock_fast(struct sock *sk) +{ + /* The sk_lock has mutex_lock() semantics here. */ + mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_); + + return __lock_sock_fast(sk); +} + +/* fast socket lock variant for caller already holding a [different] socket lock */ +static inline bool lock_sock_fast_nested(struct sock *sk) +{ + mutex_acquire(&sk->sk_lock.dep_map, SINGLE_DEPTH_NESTING, 0, _RET_IP_); + + return __lock_sock_fast(sk); +} /** * unlock_sock_fast - complement of lock_sock_fast -- cgit v1.2.3-59-g8ed1b From 35306eb23814444bd4021f8a1c3047d3cb0c8b2b Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 29 Sep 2021 15:57:50 -0700 Subject: af_unix: fix races in sk_peer_pid and sk_peer_cred accesses Jann Horn reported that SO_PEERCRED and SO_PEERGROUPS implementations are racy, as af_unix can concurrently change sk_peer_pid and sk_peer_cred. In order to fix this issue, this patch adds a new spinlock that needs to be used whenever these fields are read or written. Jann also pointed out that l2cap_sock_get_peer_pid_cb() is currently reading sk->sk_peer_pid which makes no sense, as this field is only possibly set by AF_UNIX sockets. We will have to clean this in a separate patch. This could be done by reverting b48596d1dc25 "Bluetooth: L2CAP: Add get_peer_pid callback" or implementing what was truly expected. Fixes: 109f6e39fa07 ("af_unix: Allow SO_PEERCRED to work across namespaces.") Signed-off-by: Eric Dumazet Reported-by: Jann Horn Cc: Eric W. Biederman Cc: Luiz Augusto von Dentz Cc: Marcel Holtmann Signed-off-by: David S. Miller --- include/net/sock.h | 2 ++ net/core/sock.c | 32 ++++++++++++++++++++++++++------ net/unix/af_unix.c | 34 ++++++++++++++++++++++++++++------ 3 files changed, 56 insertions(+), 12 deletions(-) (limited to 'include/net/sock.h') diff --git a/include/net/sock.h b/include/net/sock.h index dc3f8169312e..ae929e21a376 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -488,8 +488,10 @@ struct sock { u8 sk_prefer_busy_poll; u16 sk_busy_poll_budget; #endif + spinlock_t sk_peer_lock; struct pid *sk_peer_pid; const struct cred *sk_peer_cred; + long sk_rcvtimeo; ktime_t sk_stamp; #if BITS_PER_LONG==32 diff --git a/net/core/sock.c b/net/core/sock.c index 7060d183216e..c1601f75ec4b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1376,6 +1376,16 @@ set_sndbuf: } EXPORT_SYMBOL(sock_setsockopt); +static const struct cred *sk_get_peer_cred(struct sock *sk) +{ + const struct cred *cred; + + spin_lock(&sk->sk_peer_lock); + cred = get_cred(sk->sk_peer_cred); + spin_unlock(&sk->sk_peer_lock); + + return cred; +} static void cred_to_ucred(struct pid *pid, const struct cred *cred, struct ucred *ucred) @@ -1552,7 +1562,11 @@ int sock_getsockopt(struct socket *sock, int level, int optname, struct ucred peercred; if (len > sizeof(peercred)) len = sizeof(peercred); + + spin_lock(&sk->sk_peer_lock); cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred); + spin_unlock(&sk->sk_peer_lock); + if (copy_to_user(optval, &peercred, len)) return -EFAULT; goto lenout; @@ -1560,20 +1574,23 @@ int sock_getsockopt(struct socket *sock, int level, int optname, case SO_PEERGROUPS: { + const struct cred *cred; int ret, n; - if (!sk->sk_peer_cred) + cred = sk_get_peer_cred(sk); + if (!cred) return -ENODATA; - n = sk->sk_peer_cred->group_info->ngroups; + n = cred->group_info->ngroups; if (len < n * sizeof(gid_t)) { len = n * sizeof(gid_t); + put_cred(cred); return put_user(len, optlen) ? -EFAULT : -ERANGE; } len = n * sizeof(gid_t); - ret = groups_to_user((gid_t __user *)optval, - sk->sk_peer_cred->group_info); + ret = groups_to_user((gid_t __user *)optval, cred->group_info); + put_cred(cred); if (ret) return ret; goto lenout; @@ -1935,9 +1952,10 @@ static void __sk_destruct(struct rcu_head *head) sk->sk_frag.page = NULL; } - if (sk->sk_peer_cred) - put_cred(sk->sk_peer_cred); + /* We do not need to acquire sk->sk_peer_lock, we are the last user. */ + put_cred(sk->sk_peer_cred); put_pid(sk->sk_peer_pid); + if (likely(sk->sk_net_refcnt)) put_net(sock_net(sk)); sk_prot_free(sk->sk_prot_creator, sk); @@ -3145,6 +3163,8 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_peer_pid = NULL; sk->sk_peer_cred = NULL; + spin_lock_init(&sk->sk_peer_lock); + sk->sk_write_pending = 0; sk->sk_rcvlowat = 1; sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index f505b89bda6a..efac5989edb5 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -608,20 +608,42 @@ static void unix_release_sock(struct sock *sk, int embrion) static void init_peercred(struct sock *sk) { - put_pid(sk->sk_peer_pid); - if (sk->sk_peer_cred) - put_cred(sk->sk_peer_cred); + const struct cred *old_cred; + struct pid *old_pid; + + spin_lock(&sk->sk_peer_lock); + old_pid = sk->sk_peer_pid; + old_cred = sk->sk_peer_cred; sk->sk_peer_pid = get_pid(task_tgid(current)); sk->sk_peer_cred = get_current_cred(); + spin_unlock(&sk->sk_peer_lock); + + put_pid(old_pid); + put_cred(old_cred); } static void copy_peercred(struct sock *sk, struct sock *peersk) { - put_pid(sk->sk_peer_pid); - if (sk->sk_peer_cred) - put_cred(sk->sk_peer_cred); + const struct cred *old_cred; + struct pid *old_pid; + + if (sk < peersk) { + spin_lock(&sk->sk_peer_lock); + spin_lock_nested(&peersk->sk_peer_lock, SINGLE_DEPTH_NESTING); + } else { + spin_lock(&peersk->sk_peer_lock); + spin_lock_nested(&sk->sk_peer_lock, SINGLE_DEPTH_NESTING); + } + old_pid = sk->sk_peer_pid; + old_cred = sk->sk_peer_cred; sk->sk_peer_pid = get_pid(peersk->sk_peer_pid); sk->sk_peer_cred = get_cred(peersk->sk_peer_cred); + + spin_unlock(&sk->sk_peer_lock); + spin_unlock(&peersk->sk_peer_lock); + + put_pid(old_pid); + put_cred(old_cred); } static int unix_listen(struct socket *sock, int backlog) -- cgit v1.2.3-59-g8ed1b